© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2631
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to death and dying

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word "death"

    np_token-act-pair-logits · gpt-4o-mini

    death

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createState
    -0.62
     समीक्षक
    -0.58
     oprot
    -0.56
     Momb
    -0.52
    Vlastnosti
    -0.52
     تانيه
    -0.52
    setVerticalGroup
    -0.51
    Népesség
    -0.50
     betweenstory
    -0.50
     arrivare
    -0.50
    POSITIVE LOGITS
     nakalista
    0.75
    NameInMap
    0.62
    principalColumn
    0.57
    NewRow
    0.55
     Cla
    0.51
    mok
    0.49
    Архівовано
    0.48
    MLLoader
    0.47
    verwijspagina
    0.47
    গ্র
    0.47
    Activations Density 1.414%

    No Known Activations